{
  "best_metric": 2.0081570148468018,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.32232070910556004,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0064464141821112,
      "grad_norm": 2.7321786880493164,
      "learning_rate": 5e-05,
      "loss": 2.5383,
      "step": 1
    },
    {
      "epoch": 0.0064464141821112,
      "eval_loss": 2.5283396244049072,
      "eval_runtime": 2.5159,
      "eval_samples_per_second": 19.874,
      "eval_steps_per_second": 5.167,
      "step": 1
    },
    {
      "epoch": 0.0128928283642224,
      "grad_norm": 2.698495864868164,
      "learning_rate": 0.0001,
      "loss": 2.5499,
      "step": 2
    },
    {
      "epoch": 0.019339242546333603,
      "grad_norm": 1.8402256965637207,
      "learning_rate": 9.990365154573717e-05,
      "loss": 2.3426,
      "step": 3
    },
    {
      "epoch": 0.0257856567284448,
      "grad_norm": 0.5552679896354675,
      "learning_rate": 9.961501876182148e-05,
      "loss": 2.1694,
      "step": 4
    },
    {
      "epoch": 0.032232070910556,
      "grad_norm": 0.8432245850563049,
      "learning_rate": 9.913533761814537e-05,
      "loss": 2.0676,
      "step": 5
    },
    {
      "epoch": 0.038678485092667206,
      "grad_norm": 0.7348294854164124,
      "learning_rate": 9.846666218300807e-05,
      "loss": 2.0469,
      "step": 6
    },
    {
      "epoch": 0.045124899274778404,
      "grad_norm": 0.4715188443660736,
      "learning_rate": 9.761185582727977e-05,
      "loss": 1.9357,
      "step": 7
    },
    {
      "epoch": 0.0515713134568896,
      "grad_norm": 0.39538440108299255,
      "learning_rate": 9.657457896300791e-05,
      "loss": 1.7671,
      "step": 8
    },
    {
      "epoch": 0.05801772763900081,
      "grad_norm": 0.4434206187725067,
      "learning_rate": 9.535927336897098e-05,
      "loss": 1.6547,
      "step": 9
    },
    {
      "epoch": 0.064464141821112,
      "grad_norm": 0.4737102687358856,
      "learning_rate": 9.397114317029975e-05,
      "loss": 1.5741,
      "step": 10
    },
    {
      "epoch": 0.07091055600322321,
      "grad_norm": 0.5129907131195068,
      "learning_rate": 9.241613255361455e-05,
      "loss": 1.7328,
      "step": 11
    },
    {
      "epoch": 0.07735697018533441,
      "grad_norm": 0.9538379907608032,
      "learning_rate": 9.070090031310558e-05,
      "loss": 2.0174,
      "step": 12
    },
    {
      "epoch": 0.08380338436744561,
      "grad_norm": 0.42058929800987244,
      "learning_rate": 8.883279133655399e-05,
      "loss": 2.2917,
      "step": 13
    },
    {
      "epoch": 0.09024979854955681,
      "grad_norm": 0.3056967258453369,
      "learning_rate": 8.681980515339464e-05,
      "loss": 2.1605,
      "step": 14
    },
    {
      "epoch": 0.09669621273166801,
      "grad_norm": 0.30461686849594116,
      "learning_rate": 8.467056167950311e-05,
      "loss": 2.0701,
      "step": 15
    },
    {
      "epoch": 0.1031426269137792,
      "grad_norm": 0.33966585993766785,
      "learning_rate": 8.239426430539243e-05,
      "loss": 2.0992,
      "step": 16
    },
    {
      "epoch": 0.1095890410958904,
      "grad_norm": 0.364210844039917,
      "learning_rate": 8.000066048588211e-05,
      "loss": 1.9916,
      "step": 17
    },
    {
      "epoch": 0.11603545527800162,
      "grad_norm": 0.4053061008453369,
      "learning_rate": 7.75e-05,
      "loss": 1.9666,
      "step": 18
    },
    {
      "epoch": 0.12248186946011282,
      "grad_norm": 0.4174206256866455,
      "learning_rate": 7.490299105985507e-05,
      "loss": 1.9286,
      "step": 19
    },
    {
      "epoch": 0.128928283642224,
      "grad_norm": 0.37758609652519226,
      "learning_rate": 7.222075445642904e-05,
      "loss": 1.8147,
      "step": 20
    },
    {
      "epoch": 0.13537469782433523,
      "grad_norm": 0.45445677638053894,
      "learning_rate": 6.946477593864228e-05,
      "loss": 1.6091,
      "step": 21
    },
    {
      "epoch": 0.14182111200644643,
      "grad_norm": 0.42483848333358765,
      "learning_rate": 6.664685702961344e-05,
      "loss": 1.5241,
      "step": 22
    },
    {
      "epoch": 0.14826752618855762,
      "grad_norm": 0.3693537414073944,
      "learning_rate": 6.377906449072578e-05,
      "loss": 1.5441,
      "step": 23
    },
    {
      "epoch": 0.15471394037066882,
      "grad_norm": 0.5647397637367249,
      "learning_rate": 6.087367864990233e-05,
      "loss": 1.7255,
      "step": 24
    },
    {
      "epoch": 0.16116035455278002,
      "grad_norm": 0.976772665977478,
      "learning_rate": 5.794314081535644e-05,
      "loss": 2.1579,
      "step": 25
    },
    {
      "epoch": 0.16116035455278002,
      "eval_loss": 2.0506653785705566,
      "eval_runtime": 2.7588,
      "eval_samples_per_second": 18.124,
      "eval_steps_per_second": 4.712,
      "step": 25
    },
    {
      "epoch": 0.16760676873489122,
      "grad_norm": 0.2957329750061035,
      "learning_rate": 5.500000000000001e-05,
      "loss": 2.1601,
      "step": 26
    },
    {
      "epoch": 0.17405318291700242,
      "grad_norm": 0.3870042562484741,
      "learning_rate": 5.205685918464356e-05,
      "loss": 2.1707,
      "step": 27
    },
    {
      "epoch": 0.18049959709911362,
      "grad_norm": 0.4386121332645416,
      "learning_rate": 4.912632135009769e-05,
      "loss": 2.1331,
      "step": 28
    },
    {
      "epoch": 0.18694601128122482,
      "grad_norm": 0.39181363582611084,
      "learning_rate": 4.6220935509274235e-05,
      "loss": 2.0152,
      "step": 29
    },
    {
      "epoch": 0.19339242546333602,
      "grad_norm": 0.3686964511871338,
      "learning_rate": 4.3353142970386564e-05,
      "loss": 1.988,
      "step": 30
    },
    {
      "epoch": 0.1998388396454472,
      "grad_norm": 0.29318711161613464,
      "learning_rate": 4.053522406135775e-05,
      "loss": 1.921,
      "step": 31
    },
    {
      "epoch": 0.2062852538275584,
      "grad_norm": 0.25432685017585754,
      "learning_rate": 3.777924554357096e-05,
      "loss": 1.8818,
      "step": 32
    },
    {
      "epoch": 0.2127316680096696,
      "grad_norm": 0.2645367681980133,
      "learning_rate": 3.509700894014496e-05,
      "loss": 1.6544,
      "step": 33
    },
    {
      "epoch": 0.2191780821917808,
      "grad_norm": 0.3327176868915558,
      "learning_rate": 3.250000000000001e-05,
      "loss": 1.6184,
      "step": 34
    },
    {
      "epoch": 0.22562449637389204,
      "grad_norm": 0.3988659083843231,
      "learning_rate": 2.9999339514117912e-05,
      "loss": 1.5877,
      "step": 35
    },
    {
      "epoch": 0.23207091055600323,
      "grad_norm": 0.43848198652267456,
      "learning_rate": 2.760573569460757e-05,
      "loss": 1.656,
      "step": 36
    },
    {
      "epoch": 0.23851732473811443,
      "grad_norm": 0.45370516180992126,
      "learning_rate": 2.53294383204969e-05,
      "loss": 1.7091,
      "step": 37
    },
    {
      "epoch": 0.24496373892022563,
      "grad_norm": 0.2955451011657715,
      "learning_rate": 2.3180194846605367e-05,
      "loss": 2.2995,
      "step": 38
    },
    {
      "epoch": 0.25141015310233683,
      "grad_norm": 0.22161364555358887,
      "learning_rate": 2.1167208663446025e-05,
      "loss": 2.1828,
      "step": 39
    },
    {
      "epoch": 0.257856567284448,
      "grad_norm": 0.20898936688899994,
      "learning_rate": 1.9299099686894423e-05,
      "loss": 2.0718,
      "step": 40
    },
    {
      "epoch": 0.26430298146655923,
      "grad_norm": 0.21196404099464417,
      "learning_rate": 1.758386744638546e-05,
      "loss": 2.0584,
      "step": 41
    },
    {
      "epoch": 0.27074939564867045,
      "grad_norm": 0.22556056082248688,
      "learning_rate": 1.602885682970026e-05,
      "loss": 1.9672,
      "step": 42
    },
    {
      "epoch": 0.2771958098307816,
      "grad_norm": 0.23540279269218445,
      "learning_rate": 1.464072663102903e-05,
      "loss": 1.9657,
      "step": 43
    },
    {
      "epoch": 0.28364222401289285,
      "grad_norm": 0.24278955161571503,
      "learning_rate": 1.3425421036992098e-05,
      "loss": 1.8461,
      "step": 44
    },
    {
      "epoch": 0.290088638195004,
      "grad_norm": 0.25087326765060425,
      "learning_rate": 1.2388144172720251e-05,
      "loss": 1.7728,
      "step": 45
    },
    {
      "epoch": 0.29653505237711525,
      "grad_norm": 0.2805509567260742,
      "learning_rate": 1.1533337816991932e-05,
      "loss": 1.5961,
      "step": 46
    },
    {
      "epoch": 0.3029814665592264,
      "grad_norm": 0.29253560304641724,
      "learning_rate": 1.0864662381854632e-05,
      "loss": 1.5046,
      "step": 47
    },
    {
      "epoch": 0.30942788074133765,
      "grad_norm": 0.3235175907611847,
      "learning_rate": 1.0384981238178534e-05,
      "loss": 1.623,
      "step": 48
    },
    {
      "epoch": 0.3158742949234488,
      "grad_norm": 0.3595404326915741,
      "learning_rate": 1.0096348454262845e-05,
      "loss": 1.7437,
      "step": 49
    },
    {
      "epoch": 0.32232070910556004,
      "grad_norm": 0.821505069732666,
      "learning_rate": 1e-05,
      "loss": 1.9639,
      "step": 50
    },
    {
      "epoch": 0.32232070910556004,
      "eval_loss": 2.0081570148468018,
      "eval_runtime": 2.7511,
      "eval_samples_per_second": 18.175,
      "eval_steps_per_second": 4.725,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 1,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.68015399030358e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}